© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16344
    Prev
    Next
    INDEX
    Explanations

    in the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñīе
    -0.20
    çĶ¨å¾®ä¿¡
    -0.19
    åıŁ
    -0.19
     Ñģебе
    -0.18
    inge
    -0.18
    åŃļ
    -0.18
    åľ°åŁŁ
    -0.18
     вÑĭпÑĥÑģк
    -0.18
     ÑĤеÑĢÑĢиÑĤоÑĢ
    -0.17
    âľİ
    -0.17
    POSITIVE LOGITS
    ãĢĬ
    0.25
    <<
    0.21
    æľ¬æ¬¡
    0.21
     bÃłi
    0.20
    ä½ľåĵģ
    0.20
    æľ¬ä¹¦
    0.19
     ìĬ¤ìĬ¤
    0.19
    书ä¸Ń
    0.19
     subsequent
    0.19
    è¿Ļç¯ĩ
    0.19
    Activations Density 0.306%

    No Known Activations